About MCP Client
MCP Client is a sample client connecting to MCP servers to provide Claude with tools, supporting Python and JavaScript servers.
Key features
- 01MCP server connection
- 02Tool retrieval
- 03Tool execution
- 04Interactive CLI
Use cases
- 01Demonstrate MCP integration with Claude APIs
- 02Extend Claude with custom tools
- 03Learn MCP client implementation
MCP support
The client retrieves tool descriptions from MCP servers, enabling Claude to use them to answer user queries.
Details
From the project READMEMCP Client
This is a Model Context Protocol (MCP) client that allows you to interact with MCP servers, enabling Claude to use tools provided by these servers.
Prerequisites
- Python 3.11 or higher
- An Anthropic API key (set in
.envfile)
Setup
-
Clone this repository
-
Ensure you have the required dependencies installed:
pip install anthropic mcp python-dotenvOr use uv:
uv pip install anthropic mcp python-dotenv -
Set up your Anthropic API key in a
.envfile:ANTHROPIC_API_KEY=your_api_key_here
Usage
Run the client by providing the path to an MCP server script:
python client.py path/to/server_script.py
The client supports both Python and JavaScript MCP servers:
python client.py path/to/server_script.js
How It Works
- The client connects to the specified MCP server
- It retrieves available tools from the server
- When you enter a query, it's sent to Claude along with tool descriptions
- Claude decides which tools to use
- The client executes tool calls through the server
- Results are sent back to Claude for a final response
Features
- Interactive command-line interface
- Support for both Python and Node.js MCP servers
- Proper resource management and error handling
- Seamless integration with Claude's tool-use capabilities
Troubleshooting
- If you encounter connection issues, verify the server path and ensure the server is running
- The first response might take up to 30 seconds due to initialization
- For more detailed logs, check the server output
Resources
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.